Dynamic Graph Models Detect Anomalies in 5G Networks
Original title: Explainable Anomaly Detection in 5G Networks through Continuous Time Graphs
Proposes dynamic graph formalism for 5G anomaly detection capturing packet-level content and contexts.
5G networks are formalized as dynamic graphs for anomaly detection. Techniques from graph-based learning applied to identify sophisticated attacks. Evaluation with popular dynamic graph models shows potential.
- 5G networks resemble distributed systems
- Fine-grained packet-level semantic analysis
- Captures sequential and topological contexts
- Evaluated on most popular dynamic graph models
From the original article
1 min read at arxiv.org5G networks increasingly resemble distributed systems in their design. It then becomes crucial to move beyond traditional network-based detection methods and to explore alternative approaches. In this work, we propose a formalization of 5G network exchanges as a dynamic graph, on which we apply techniques from the field of graph-based learning to detect anomalies effectively.
By Thomas Hoger · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.